AMD quits benchmark group, implying benchmarks are Intel biased!; nVidia quits too

[Vyom]

AMD quits benchmark group, implying Intel bias

Advanced Micro Devices has quit a PC industry consortium, implying the integrity of a widely used benchmark is biased toward Intel chips.
In a blog Wednesday, an AMD executive provided a long explanation about why AMD has quit the BAPCo industry consortium, which develops and distributes the SYSmark benchmark.
"Customers need clear and reliable measurements to understand the expected performance and value of their systems," Nigel Dessau, senior vice president and chief marketing officer at AMD, said in a statement. "AMD does not believe SM2012 (SYSMark 2012) achieves this objective. Hence AMD cannot endorse or support SM2012 or remain part of the BAPCo consortium."
Graphics chip supplier Nvidia has also quit the group. The company confirmed to CNET that it has quit but declined to comment further.
AMD's argument revolves around the lack of emphasis on what is called general-purpose computing on graphics processing units, or GPGPU. This is an evolving computing paradigm that attaches increasing importance to the GPU for accelerating common tasks such as encoding/decoding of video and audio and Web browsing.
Dessau continued. "SM2012 doesn't represent the evolution of computer processing...SM2012 focuses only on the serial processing performance of the CPU, and virtually ignores the parallel processing performance of the GPU." Serial processing refers to the computation done on the main central processing unit, or CPU.
AMD's newest "Llano" chips allocate roughly equal real estate to the CPU and GPU, a break from the past when AMD processors were mostly composed of circuits devoted to the CPU. Intel still allocates more real estate to the CPU than the GPU component.
BAPCo responded to AMD's accusations. "Each member in BAPCo gets one vote on any proposals made by member companies. AMD voted in support of over 80% of the SYSmark 2012 development milestones, and were supported by BAPCo in 100% of the SYSmark 2012 proposals they put forward to the consortium...BAPCo never threatened AMD with expulsion from the consortium."
And AMD is certainly not the only company that provides input to the group. Members with equal standing include Microsoft, Dell, Hewlett-Packard, Lenovo, Samsung, Sony, and Toshiba. And, of course, Intel.
"It is a democratic process," Intel spokesman Dan Snyder said. "Intel believes that no single benchmark alone is a definitive measure of a PC's performance. Intel encourages all technical reviewers to use multiple benchmarks and applications--synthetic and real world--in determining the performance of a PC," he said in an e-mail.
Moreover, Intel is moving increasingly in the same direction of AMD and Nvidia. With its newest Sandy Bridge generation, Intel has, for the first time in a mainstream chip, integrated graphics processing silicon onto the main processor. And Intel will continue to beef up graphics processing on its upcoming Ivy Bridge chips, due late this year.

Are you in favor of AMD decision? Or just think, AMD chickened out!!

[tkin]

ROFL, we are slowly getting an idea of the performance of bulldozer, good thing I bought the 2600k early, their prices will go up after BD launch as most people will buy sandys.

Good knowing you amd, its been a pleasure.

Graphics chip supplier Nvidia has also quit the group. The company confirmed to CNET that it has quit but declined to comment further.
AMD's argument revolves around the lack of emphasis on what is called general-purpose computing on graphics processing units, or GPGPU. This is an evolving computing paradigm that attaches increasing importance to the GPU for accelerating common tasks such as encoding/decoding of video and audio and Web browsing.
Dessau continued. "SM2012 doesn't represent the evolution of computer processing...SM2012 focuses only on the serial processing performance of the CPU, and virtually ignores the parallel processing performance of the GPU." Serial processing refers to the computation done on the main central processing unit, or CPU.
AMD's newest "Llano" chips allocate roughly equal real estate to the CPU and GPU, a break from the past when AMD processors were mostly composed of circuits devoted to the CPU. Intel still allocates more real estate to the CPU than the GPU component.

Looks like they are still hanging on to their gpu performance, heres an idea, get a cpu that performs like a pentium and pair it with a 6990, it'll play games, its only that it will take hours to calculate 2+2 on a calculator

[Tech&ME]

ha ha!

That's very simple. AMD themselves explained how chickened out they were from the consortium.

I have never liked to work on AMD based machines!
Even Apple adopted Intel based processor for their Macs !!

[ssk_the_gr8]

Originally Posted by vineet369

AMD quits benchmark group, implying Intel bias




Are you in favor of AMD decision? Or just think, AMD chickened out!!

this is a very old story, there was the case of intel compilers automatically degrading performance when used with an amd cpu, these are old habits of intel .. most of the benchmarks favour intel.. they have the money to make that happen.. AMD,Nvidia,Via should have quit a long time ago

[Vyom]

Why Intel compilers? Shouldn't there be a standard Compiler, made by a third party, and no way related to AMD or Intel, to benchmark both processors!

[ssk_the_gr8]

Intel had made compilers which were good , so everybody was using it but the problem is intel coded it to degrade performance on purpose whenever it detected an amd cpu!

[noob]

Originally Posted by ssk_the_gr8

Intel had made compilers which were good , so everybody was using it but the problem is intel coded it to degrade performance on purpose whenever it detected an amd cpu!

this is what you think dear....however its not so..prove what you say...

[Piyush]

Originally Posted by talktoanil

this is what you think dear....however its not so..prove what you say...

money makes everything possible
and how can anyone prove the above statement
if it had been proved, then we would have been hearing/seeing something else on the board

[shantanu]

Yeah ! this is an old news, I guess AMD should have quit this a long time back. AMD is and always have been my favourite proccy. Still using their QUad and its really good. Every thing that i throw on the machine runs superbly. Intel on the other hand has the money power and can tweak anything with that power.

[Liverpool_fan]

Originally Posted by tkin

ROFL, we are slowly getting an idea of the performance of bulldozer, good thing I bought the 2600k early, their prices will go up after BD launch as most people will buy sandys.

Good knowing you amd, its been a pleasure.


Looks like they are still hanging on to their gpu performance, heres an idea, get a cpu that performs like a pentium and pair it with a 6990, it'll play games, its only that it will take hours to calculate 2+2 on a calculator

Originally Posted by Tech&ME

ha ha!

That's very simple. AMD themselves explained how chickened out they were from the consortium.

Very easy to make conclusions isn't it?

I have never liked to work on AMD based machines!

May I know the reason?

Even Apple adopted Intel based processor for their Macs !!

They chose it way back when AMDs were the leading force.

Originally Posted by ssk_the_gr8

Intel had made compilers which were good , so everybody was using it but the problem is intel coded it to degrade performance on purpose whenever it detected an amd cpu!

More like the Intel compilers were optimized for Intel processors rather than "degrading" for AMD chips. ANd that's quite obvious, if you write any software, you'll make sure it works best in your hardware.

[ico]

First of all, synthetic benchmarks are useless. Made no difference when they were supporting it, makes no difference now.

From their perspective, I'd say they did the right job by quitting when Intel was dominating BAPCo. Intel funds the most to BAPCo.

Originally Posted by Liverpool_fan

More like the Intel compilers were optimized for Intel processors rather than "degrading" for AMD chips. ANd that's quite obvious, if you write any software, you'll make sure it works best in your hardware.

Well, performance increase by just a change of CPUID is weird? Isn't it?

Intel Forced to Remove "Cripple AMD" Function from Compiler?

[ssk_the_gr8]

Originally Posted by Liverpool_fan

More like the Intel compilers were optimized for Intel processors rather than "degrading" for AMD chips. ANd that's quite obvious, if you write any software, you'll make sure it works best in your hardware.

know your facts before saying anything, like i did
check out ico's post.. do a search u'll find more proof

[ico]

Originally Posted by Liverpool_fan

They chose it way back when AMDs were the leading force.

Actually, when AMD was leading Apple used PowerPC.

[Liverpool_fan]

Yeah, Intel are susceptible to that as well. I guess we should talk about this case, when people completely deny Intel bias.

Originally Posted by ssk_the_gr8

know your facts before saying anything, like i did
check out ico's post.. do a search u'll find more proof

Ok. I stand corrected. It more so proves your point.

[ssk_the_gr8]

Originally Posted by talktoanil

this is what you think dear....however its not so..prove what you say...

Originally Posted by Piyush

money makes everything possible
and how can anyone prove the above statement
if it had been proved, then we would have been hearing/seeing something else on the board

both of you can also check out ico's post... do a search u'll find a lot more..
they paid OEMs not to carry amd cpus etc... gave them discounts if they sold intel exclusively

&,that is why the EU union did an antitrust case on intel, even japan and south korea did it.
intel has done a lot of misdeeds to stay in this dominant position..

[asingh]

I think it is fair on AMD's part to walk off. Why support a synthetic architecture which is against the grain of their design, and then be shown as a looser.

[kamal_saran]

amd should quit it long time ago. . . . But i didn't get the idea that why nvidia and via leave it . . . . .

[ssk_the_gr8]

Originally Posted by kamal_saran

amd should quit it long time ago. . . . But i didn't get the idea that why nvidia and via leave it . . . . .

same reasons... benchmarks favoured intel

[Piyush]

Originally Posted by ssk_the_gr8

both of you can also check out ico's post... do a search u'll find a lot more..
they paid OEMs not to carry amd cpus etc... gave them discounts if they sold intel exclusively

&,that is why the EU union did an antitrust case on intel, even japan and south korea did it.
intel has done a lot of misdeeds to stay in this dominant position..

thats what i was saying

[Tech&ME]

Ya , many companies do misdeeds to benefit themselves. This a very common practice. Microsoft also did such things with IE. They included IE FREE with their OS and pushed Net Scape down. (I know many members here doesn't know about Net Scape because it was the FIRST browser to hit the internet., back then)

An AntiTrust lawsuit was filed against Microsoft back then. See this

So the MONOPOLY in business is always there.

Intel did its bits to gain market share against AMD and VIA.

And IT WAS A VERY BIG NEWS those days BBC World carried a Media Trial on it.

[tkin]

Originally Posted by ssk_the_gr8

Intel had made compilers which were good , so everybody was using it but the problem is intel coded it to degrade performance on purpose whenever it detected an amd cpu!

Isn't this an old myth debunked long ago? The same was with tessellation and fermi when amd released 58xx series, when fermi toppled the tess benchmarks amd said they were using too much tess etc.

PS: Before Core 2 architecture amd was kicking intel's @$$ very much(loved those days), why couldn't they release good compilers back then? I don't believe this at all.

Originally Posted by asingh

I think it is fair on AMD's part to walk off. Why support a synthetic architecture which is against the grain of their design, and then be shown as a looser.

While I agree synthetic benchmarks do not hold in real life but in cpu world they match apps very much, not so in GPU(3d mark? bah, never proved anything). Plus look at the resent comparison between amd and intel(sandy/nehalem vs phenom), intel dominates every single benchmark, including the non synthetics.

In 3d mark nvidia loses to amd but in games they push ahead, so synthetic benchmarks are questionable for 3d cards, but in cpu world they scale as in proper apps.

[asingh]

3D mark is like 2 generations old...! Vantage 2010 and '11 have come out. 3D mark was famous for being CPU bound when touted as a GPU synthetic...!

Now what..!

[tkin]

Originally Posted by asingh

3D mark is like 2 generations old...! Vantage 2010 and '11 have come out. 3D mark was famous for being CPU bound when touted as a GPU synthetic...!

Now what..!

Still amd wins in both cases(comparable cards like say 560 and 6950 2GB), but in games they are very close and in some cases they nvidia triumphs amd.

[ico]

Point is, Intel makes better chips? Yes, everyone knows this. But rigged synthetic benchmarks exaggerate the difference.

[tkin]

Originally Posted by ico

Point is, Intel makes better chips? Yes, everyone knows this. But rigged synthetic benchmarks exaggerate the difference.

I can live with that, but people claiming amd is faster and lose ONLY due to compilers is a blatant lie.

[ico]

Originally Posted by tkin

I can live with that, but people claiming amd is faster and lose ONLY due to compilers is a blatant lie.

No one has claimed that. They are just talking about Intel's track record.

[tkin]

Originally Posted by ico

No one has claimed that. They are just talking about Intel's track record.

Okie dokie, on a side note, your sig is pure evil